Pattern labeling

1. A method comprising: by a computing device, accessing a log associated with a user, the log comprising a plurality of entries that each indicate a geo-location of the user at a particular time of day of a particular day of a week, each of at least some of the data points being based on a geo-location determined and reported by a mobile computing device of the user without manual user input; by the computing device, determining one or more geo-location centroids based on a distance between the respective geo-location centroid and each of the geo-location data points, wherein each geo-location centroid is representative of the plurality of geo-location data points obtained during the particular time of day of the particular day of a week; by the computing device, determining a place corresponding to each of the geo-location centroids, wherein the place corresponds to one or more particular activities; by the computing device, updating a social graph associated with the user with information associated with the activities; by the computing device, determining a spatial center of a plurality of geo-location centroids based on a distance between each geo-location centroid and its respective spatial center, each spatial center representing one or more of the plurality of geo-location centroids of the particular time of the particular day of the week; by the computing device, determining a time-based routine of the particular day of the week based at least in part on a number of spatial centers of each particular time of day of the particular day of the week, the time-based routine comprising a pattern of a plurality of spatial centers of a plurality of times of the day of the particular day of the week; and by the computing device, determining a probability that the user will be at a particular spatial center at the particular time of day of the particular day of the week based at least in part on the number of geo-location centroids being represented by the particular spatial center.

2. The method of claim 1 , the method further comprising inferring by the computing device the user is employed at a particular business based at least in part on a number of entries corresponding to a geo-location of the particular business at past points of time corresponding to working hours.

3. The method of claim 1 , wherein the place comprises a residence, grocery store, restaurant, supermarket, sporting venue, landmark, freeway, movie theater, or place of employment.

4. The method of claim 3 , wherein the activity comprises working, patronizing, residing, attending an event, or visiting.

5. The method of claim 1 , wherein: the social graph comprises a plurality of nodes and edges connecting the nodes; and at least one node in the graph corresponding to the user.

6. One or more computer-readable non-transitory storage media storing computer-readable instructions which when executed by a processor device, cause to processor device to: access a log associated with a user, the log comprising a plurality of entries that each indicate a geo-location of the user at a particular time of day of a particular day of a week, each of at least some of the data points being based on a geo-location determined and reported by a mobile computing device of the user without manual user input; determine one or more geo-location centroids based on a distance between the respective geo-location centroid and each of the geo-location data points, wherein each geo-location centroid is representative of the plurality of geo-location data points obtained during the particular time of day of the particular day of a week: determine a place corresponding to each of the geo-location centroids, wherein the place corresponds to one or more particular activities; update a social graph associated with the user with information associated with the activities; determine a spatial center of a plurality of geo-location centroids based on a distance between each geo-location centroid and its respective spatial center, each spatial center representing one or more of the plurality of geo-location centroids of the particular time of the particular day of the week; determine a time-based routine of the particular day of the week based at least in part on a number of spatial centers of each particular time of day of the particular day of the week, the time-based routine comprising a pattern of a plurality of spatial centers of a plurality of times of the day of the particular day of the week; and determine a probability that the user will be at a particular spatial center at the particular time of day of the particular day of the week based at least in part on the number of geo-location centroids being represented by the particular spatial center.

7. The media of claim 6 , comprising instructions to infer the user is employed at a particular business based at least in part on a number of entries corresponding to a geo-location of the particular business at past points of time corresponding to working hours.

8. The media of claim 6 , wherein the place comprises a residence, grocery store, restaurant, supermarket, sporting venue, landmark, freeway, movie theater, or place of employment.

9. The media of claim 8 , wherein the activity comprises working, patronizing, residing, attending an event, or visiting.

10. The media of claim 6 , wherein the social graph comprises a plurality of nodes and edges connecting the nodes; and at least one node in the graph corresponding to the user.

11. A device comprising: one or more processors; and one or more computer-readable non-transitory storage media coupled to the processors and embodying software configured when executed to: access a log associated with a user, the log comprising a plurality of entries that each indicate a geo-location of the user at a particular time of day of a particular day of a week, each of at least some of the data points being based on a geo-location determined and reported by a mobile computing device of the user without manual user input; determine one or more geo-location centroids based on a distance between the respective geo-location centroid and each of the geo-location data points, wherein each geo-location centroid is representative of the plurality of geo-location data points obtained during the particular time of day of the particular day of a week; determine a place corresponding to each of the geo-location centroids, wherein the place corresponds to one or more particular activities; update a social graph associated with the user with information associated with the activities; determine a spatial center of a plurality of geo-location centroids based on a distance between each geo-location centroid and its respective spatial center, each spatial center representing one or more of the plurality of geo-location centroids of the particular time of the particular day of the week; determine a time-based routine of the particular day of the week based at least in part on a number of spatial centers of each particular time of day of the particular day of the week, the time-based routine comprising a pattern of a plurality of spatial centers of a plurality of times of the day of the particular day of the week; and determine a probability that the user will be at a particular spatial center at the particular time of day of the particular day of the week based at least in part on the number of geo-location centroids being represented by the particular spatial center.